MMinaraiVideo-to-skill workspace
日本語

Choose source video

Video 1 · Workshop filingOpen · 8:04Video 5 · Kyoto engraverOpen · 5:40Video 6 · Dayel grinderOpen · 1:52Video 7 · DONGTAI compact grinderOpen · 2:45Video 8 · Titans ID wheelSelected · 0:59

Open questions · Human–AI collaboration

Return what the video could not tell us to the skill graph.

The AI formulates questions from the gap between what the source supports and what a learner still needs. An expert answer becomes a provenance-bearing graph node and updates the related process context.

Progress

0 / 6

01 · QUESTION FORMULATION

How an open question is formulated

The system does not plausibly fill gaps. It fixes the source-supported boundary, then asks only for learning-critical fields that remain unstated.

  1. 01
    Perceive video and speech

    Ground speech, on-screen text, entities, and motion in time

  2. 02
    Structure the graph

    Separate process, action, attention, and criteria

  3. 03
    Detect a missing field

    Find absent criteria, values, exceptions, rationale, or identity

  4. 04
    Formulate a neutral question

    Avoid leading the answer and retain source links

  5. 05
    Apply the human answer

    Add accepted evidence and mark the question resolved

02 · OPEN QUESTIONS

Open questions in the skill graph

Select a question to inspect why it was generated, its evidence, and the exact graph patch an answer will create.

Controlled identity or authority

What part numbers, compatibility rules and fully-threaded check apply?

Open
Why it was generated

The object or source wording is visible, but an approved name, part number, or governing document cannot be established from the video alone.

What the source establishes

Identify the three components — The practitioner names three RID-spindle components: main shaft, mounting arbor threaded into the shaft, and the wheel mounted after the arbor is fully threaded.

Learning-critical field missing from the source

Controlled identity or authority

Evidence IDs
v8-speech-components
0:14

Expert answer

03 · GRAPH UPDATE

Live graph patch

Applying an answer immediately changes the question state and adds a human-verified evidence node.

LEARNING UNITIdentify the three componentsRelated learning unit
RAISES_QUESTION
OPENQUESTIONWhat part numbers, compatibility rules and fully-threaded check apply?Awaiting an answer
SUPPORTED_BY
EVIDENCEITEMAwaiting an answerHuman-verified evidence

04 · SOURCE CHECKS

Supporting source checks

Transcript, OCR, and neutral-ID checks are a separate provenance gate—not answers to the skill questions. They remain available below.

Progress0 / 3

1. Audio spot checks

Listen and confirm whether the displayed source-language text matches the recording.

Audio 1

「all the way threaded in, we mount our wheel. Today we're going to be using a TeraLit RAA 100 grit pink」

segment 2 · 11.30s

Audio 2

「start with the resin then I'm going to add some hardener and I'm going to use a coffee stir stick.」

segment 6 · 31.98s

Audio 3

「epoxy in the center of the wheel. Very important to keep this wheel clean and have a good bond」

segment 9 · 48.20s

The result is bound to this video hash

0b61f470ae71fb4d191f6e0db5fe61607f6044e4551e5a42f67a8f42667c83f3

The mechanical gate remains pending until the JSON is imported with apply-human-review. Formalizing the SOP requires a separate practitioner review of every instruction.

Continue with this source

One source, five connected views

Switching views preserves the same source hash across instruction, analysis, skill structure, evidence, and human review.

01Learning guideLearn the demonstration as a visual procedure02Vision labInspect model outputs, live graph, and teaching visuals03Skill mapExplore process, tools, judgment, and learning04EvidenceReturn to speech, source text, and observations
05Open questionsAnswer knowledge gaps and update the skill graphYou are here